CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

feature-review

Reviews a PR, commit, range, or branch as a feature first and code second, in a local HTML page whose comments post back to the PR as one GitHub review. Use when the user asks to review a PR or commit, review the feature or shape of a change, or re-review a PR after new pushes: "review PR #123", "review this commit", "review the feature in PR #123", "re-review PR #123".

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary operational skill body: executable commands throughout, a clear sequenced workflow with self-check and validation built into the build step, and well-signaled one-level references verified against the actual bundle. The only room for improvement is trimming the in-body descriptions of page UI and adding an explicit error-recovery loop for failed validation.

DimensionReasoningScore

Conciseness

The body is dense and operational throughout — commands, paths, and specific behaviors with no padding and no explanation of concepts Claude already knows — but it is long, and passages describing page UI in detail (the overview's four parts, the recommendation card anatomy) could be trimmed or delegated to references. Efficient with minor instances that could be tightened, so anchor 4 rather than 5.

4 / 5

Actionability

The Usage block gives copy-paste-ready commands for every invocation mode (commit, range, PR, --since, --serve, --stdin, -o/--title/--event), the workflow names exact scripts ("node $S/pr-media.cjs --pr <N>", "node $S/review-guides.cjs") and exact files to write, and specific gotchas state what to do instead — fully executable coverage of the common cases.

5 / 5

Workflow Clarity

The six-step workflow (Gather → Load preferences → Read the change → Build → Open → Report) is clearly sequenced, with checkpoints present: the build runs a self-check and guide validation, the report step surfaces the self-check and CI lines, and failures are handled ("Skip captures when the app can't run, and say so in the report"). It stops short of anchor 5 because there is no explicit fix-and-retry feedback loop when validation fails.

4 / 5

Progressive Disclosure

The body is a genuine overview: each topic (gathering, overview format, recommendations, reading guide, page behavior, developing) is a sentence or two that clearly signals a one-level-deep reference, all eight referenced files exist in references/ and cross-link only laterally (no nested reference chains), and a Files section inventories every bundle script and reference.

5 / 5

Total

18

/

20

Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete capabilities in third person, includes an explicit Use-when clause with realistic quoted trigger phrases, and clearly delimits its niche. Its only weakness is that its most generic triggers ("review PR #123", "review this commit") overlap with plain code-review skills.

DimensionReasoningScore

Specificity

"Reviews a PR, commit, range, or branch as a feature first and code second, in a local HTML page whose comments post back to the PR as one GitHub review" names the input types, the review approach, the output medium, and the submission behavior — comprehensive concrete coverage of the skill's actions with no gaps.

5 / 5

Completeness

It explicitly answers both questions: a clear "what" (feature-first review rendered in a local HTML page whose comments post back as one GitHub review) and an explicit "Use when..." clause with concrete quoted trigger phrases, matching the anchor-5 example's structure.

5 / 5

Trigger Term Quality

The description quotes natural user phrases directly — "review PR #123", "review this commit", "review the feature in PR #123", "re-review PR #123" — and adds variations like "review the feature or shape of a change" and "re-review a PR after new pushes", covering the full range of how a user would ask for this.

5 / 5

Distinctiveness Conflict Risk

The feature-first, HTML-page, post-as-one-review, re-review framing carves a clear niche, but the bare triggers "review PR #123" and "review this commit" would also naturally match a generic code-review skill, leaving minor overlap risk with a closely related skill rather than minimal conflict risk.

4 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

RoleModel/rolemodel-skills

Path

skills/feature-review/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.